User | jackhinkle |
Upload Date | September 01 2025 12:21 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 26.0 (Build 25A5349a) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2121
394.4 IPS |
|
Image Classification (HP)
|
100% |
17693
3.29 KIPS |
|
Image Classification (Q)
|
97% |
21857
4.08 KIPS |
|
Image Segmentation (SP)
|
100% |
2299
37.3 IPS |
|
Image Segmentation (HP)
|
100% |
23530
381.4 IPS |
|
Image Segmentation (Q)
|
99% |
32654
529.4 IPS |
|
Pose Estimation (SP)
|
100% |
17140
20.0 IPS |
|
Pose Estimation (HP)
|
100% |
123094
143.6 IPS |
|
Pose Estimation (Q)
|
95% |
229611
269.1 IPS |
|
Object Detection (SP)
|
100% |
2565
203.5 IPS |
|
Object Detection (HP)
|
100% |
19991
1.59 KIPS |
|
Object Detection (Q)
|
91% |
23814
1.90 KIPS |
|
Face Detection (SP)
|
100% |
5061
60.1 IPS |
|
Face Detection (HP)
|
100% |
44691
531.0 IPS |
|
Face Detection (Q)
|
100% |
62044
737.2 IPS |
|
Depth Estimation (SP)
|
100% |
8782
67.7 IPS |
|
Depth Estimation (HP)
|
99% |
109164
841.0 IPS |
|
Depth Estimation (Q)
|
85% |
176633
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
30464
39.2 IPS |
|
Style Transfer (HP)
|
100% |
236856
304.5 IPS |
|
Style Transfer (Q)
|
96% |
325609
420.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
7054
260.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
49488
1.83 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80994
2.99 KIPS |
|
Text Classification (SP)
|
100% |
3112
4.15 KIPS |
|
Text Classification (HP)
|
99% |
5515
7.36 KIPS |
|
Text Classification (Q)
|
93% |
5355
7.19 KIPS |
|
Machine Translation (SP)
|
100% |
5876
101.2 IPS |
|
Machine Translation (HP)
|
100% |
16368
281.9 IPS |
|
Machine Translation (Q)
|
98% |
16488
284.9 IPS |